Mojo module
encodings
Implementations of quantization encodings.
Aliasesβ
- β
K_SCALE_SIZE = 12
: Size of superblock scales and mins, in bytes. - β
QK_K = 256
: Size of superblock quantized elements, in bytes.
Structsβ
- β
BFloat16Encoding
: The bfloat16 quantization encoding. - β
Float32Encoding
: The float32 quantization encoding. - β
Q4_0Encoding
: The Q4_0 quantization encoding. - β
Q4_KEncoding
: The Q4_K quantization encoding. - β
Q5_KEncoding
: The Q5_K quantization encoding. - β
Q6_KEncoding
: The Q6_K quantization encoding.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!
π What went wrong?